A Measurement-Theoretic Foundation of Rule Interestingness Evaluation

Abstract

Bien que ces formulaires aient inclus dans la pagination, il n'y aura aucun contenu manquant. CanadaReproduced with permission of the copyright owner. Further reproduction prohibited without permission. UNIVERSITY OF REGINA FACULTY OF GRADUATE STUDIES AND RESEARCH SUPERVISORY AND EXAMINING COMMITTEE Yaohua Chen, candidate for the degree of Master of Science, has presented a thesis titled, A Measurement-Theoretic Foundation of Rule Interestingness Evaluation, in an oral examination held on August 30, 2004. The following committee members have found the thesis acceptable in form and content, and that the candidate demonstrated satisfactory knowledge of the subject material.

Attribute reduction in decision-theoretic rough set models

“…Many quantitative measures associated with rules have been studied [3,5,46,49]. We review some measures for single rule (local) evaluation.…”

User-Centered Interactive Data Mining

“…Based on the contingency table, various quantitative measures can be used for rule interestingness evaluation (Yao, Chen and Yang, 2003;Yao and Zhong, 1999).…”

“…The study of different decision logic languages enables the definition of granules and concepts at the philosophy layer . The study of rule interestingness measures reveals the relationships among granules and concepts in the philosophy layer, and facilitates the discovery of interesting patterns in the technique layer (Yao, Chen and Yang, 2003;Zhong, 1999, Zhong, Yao andOhshima, 2003;Zhong, Yao, Ohshima and Ohsuga, 2001). The study of user preferences provides a formal model for involving user's judgement into the whole data mining process.…”

Using Fuzzy Semantic Log for Rough Set Web Page Recommendation

“…Finding useful information from massive web pages by rule mining is a great challenge. Web log analysis method has been widely used in finding web usage patterns [1,2], which include statistical analysis, frequency of visits, page analysis, common access paths [3] , association rules [4], and other methods. Most of data mining algorithms directly deal with raw web log data [5], analysis after a simple decomposition of the data [6], and then discover a user's usage patterns [7].…”